-
Hello Guys,
i wanted to try your version of Phi-3.5-mini-instruct with the DPO Trainer from Huggingface.
But when i run the Training i get *NaN or Inf found in input tensor.*
Same code wor…
-
The `model_downloader.py` script doesn't list the recently supported phi 3.5 moe.
I'd like to also know if it's ok to use the v0.3 release from Jul 6 as-is to run it.
Thanks!
-
Add support for this incredible model
-
- [Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)
- [Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct)
- [Phi-3.5-vision-instruct](https://…
-
### Feature request
Add support for [microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) which has `PhiMoEForCausalLM` arch.
### Motivation
It fails with the foll…
-
I find Microsoft's Phi 3.5 vision instruct performs much better than Florence 2. Since it's an instruct model, it also has the benefit of taking text instruction as input to help describing the images…
-
Hi,
I recently fine-tuned the phi-3.5-moe-instruct model and phi-3.5-mini-instruct model using PEFT LORA. It seems the Moe model is performing way worse than 3.5 Mini Are there any specific things …
-
## Describe the bug
I was trying phi 3.5 with this tool but it throws unknown error
## To Reproduce
Steps to reproduce the behavior:
1. Add phi 3.5 to the llm models folder
2. In the Answer…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports.
### Exp…
-
### Prerequisites
- [X] I am running the latest code. Mention the version if possible as well.
- [X] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md)…